AI架构演化遵循与生物进化相似的统计规律，揭示其深层结构共性。
Universal statistical signatures of evolution in artificial intelligence architectures
- 通过935次实验分析，发现架构修改的适应度效应呈重尾分布，类似生物进化。
- 68%修改有害，13%有益（远高于生物的1-6%），体现人工设计的优势。
- 多类架构独立演化多次，类比生物趋同进化，适合研究智能系统演化机制者阅读。
我们检验人工智能架构演化是否遵循与生物进化相同的统计规律。综合161篇论文中的935次消融实验，发现架构修改的适应度效应分布（DFE）符合重尾的Student's t分布，其中68%为有害，19%中性，13%有益（主消融实验n=568），该比例使AI介于紧凑病毒基因组与简单真核生物之间。DFE形态与果蝇（归一化KS=0.07）和酿酒酵母（KS=0.09）高度匹配；有益突变比例显著升高（13%对比生物1-6%），量化了定向搜索相较于盲目搜索的优势，同时保持分布形态一致。架构起源遵循逻辑斯蒂动态（R²=0.994），表现出间断平衡与适应辐射至领域生态位。14种架构特征独立出现3-5次，类比生物学趋同现象。结果表明，演化的统计结构具有载体无关性，由适应度景观拓扑决定，而非选择机制本身。
原文摘要 · Abstract (English)
We test whether artificial intelligence architectural evolution obeys the same statistical laws as biological evolution. Compiling 935 ablation experiments from 161 publications, we show that the distribution of fitness effects (DFE) of architectural modifications follows a heavy-tailed Student's t-distribution with proportions (68% deleterious, 19% neutral, 13% beneficial for major ablations, n=568) that place AI between compact viral genomes and simple eukaryotes. The DFE shape matches D. melanogaster (normalized KS=0.07) and S. cerevisiae (KS=0.09); the elevated beneficial fraction (13% vs. 1-6% in biology) quantifies the advantage of directed over blind search while preserving the distributional form. Architectural origination follows logistic dynamics (R^2=0.994) with punctuated equilibria and adaptive radiation into domain niches. Fourteen architectural traits were independently invented 3-5 times, paralleling biological convergences. These results demonstrate that the statistical structure of evolution is substrate-independent, determined by fitness landscape topology rather than the mechanism of selection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。